Search 721 technical articles covering deployment, upgrades, knowledge bases, workflows, integrations, and APIs.
Set up and use FastGPT Chat API Retrieve Your FastGPT App ID Every chat application on FastGPT has a unique App ID, a required identifier for all Chat API…
721 articles
Configure FastGPT Volume Manager Environment Variables Overview This page details the environment variables for the FastGPT Volume Manager, which are load…
Adjust WeCom Login Auto Redirect Settings Overview This document covers configuration of the WeCom login auto redirect behavior for self-hosted FastGPT de…
Clean Up Legacy FastGPT Workflow Enum Data Legacy Workflow Enum Data Issue Some historical FastGPT workflow nodes store TypeScript enum expression strings…
Migrate FastGPT Workflow V1 to V2 Data During Upgrade Eligibility for Migration Only users who deployed FastGPT versions earlier than 4.8 must complete th…
Integrate Local Models via Xinference with FastGPT Xinference Integration Overview Xinference is an open-source model inference platform that integrates w…
Integrate Qwen Local Model with FastGPT Overview FastGPT supports integration of custom local large language models via direct edits to its core configura…
Set Up M3E Embedding Models in FastGPT Core Usage Restrictions Before implementing M3E embedding models in FastGPT, note two non-modifiable constraints: F…
Deploy M3E Large Model API for FastGPT Container Image Options Two official container images are provided for running the M3E large model API. The primary…
Migrate OneAPI Channels to AI Proxy Migration Overview For users of older FastGPT deployments using OneAPI for model channel configuration, the official m…
Install and Configure MinerU for FastGPT Parsing MinerU Integration Overview The MinerU parsing service for FastGPT is distributed via a pre-built Docker…
Extract Accurate PDF Content with MinerU Core Extraction Capabilities When integrating MinerU with FastGPT for self-hosted custom model deployments, you c…
Install Ollama for FastGPT Self-Hosted Deployments Prerequisites Before deploying Ollama with FastGPT via Docker, ensure Docker is installed on your host…